Mann-Whitney U test in SciPy - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the Mann-Whitney U test used for?

It is a test to compare two groups to see if one tends to have larger values than the other, without assuming the data follows a normal distribution.

beginner

What kind of data does the Mann-Whitney U test work with?

It works with two independent samples of ordinal or continuous data that do not need to be normally distributed.

beginner

In Python's scipy library, which function performs the Mann-Whitney U test?

The function is scipy.stats.mannwhitneyu.

beginner

What does the p-value from the Mann-Whitney U test tell us?

It tells us how likely it is to see the observed difference between groups if there was actually no difference.

beginner

What is the null hypothesis in the Mann-Whitney U test?

The null hypothesis is that the two groups come from the same distribution, meaning no difference in their values.

What does the Mann-Whitney U test compare?

A Two independent groups without assuming normal distribution

B Two paired groups assuming normal distribution

C More than two groups with normal distribution

D Correlation between two variables

The Mann-Whitney U test compares two independent groups without assuming the data is normally distributed.

Which scipy function runs the Mann-Whitney U test?

A scipy.stats.ttest_ind

B scipy.stats.mannwhitneyu

C scipy.stats.chi2_contingency

D scipy.stats.pearsonr

scipy.stats.mannwhitneyu is the function for the Mann-Whitney U test.

What does a small p-value from the Mann-Whitney U test indicate?

A Strong evidence that the two groups differ

B No difference between groups

C Data is normally distributed

D Test was not performed correctly

A small p-value means strong evidence against the null hypothesis, suggesting the groups differ.

Which assumption is NOT required for the Mann-Whitney U test?

A Samples are independent

B Groups have similar shapes

C Data is ordinal or continuous

D Data is normally distributed

The Mann-Whitney U test does NOT require data to be normally distributed.

If the Mann-Whitney U test returns U=0, what does it mean?

A Test failed to run

B Both groups have identical values

C One group has all smaller values than the other

D Groups are perfectly correlated

U=0 means all values in one group are smaller than all values in the other group.

Explain in your own words what the Mann-Whitney U test does and when you would use it.

Think about comparing two groups when you can't assume normal data.

Describe how to perform the Mann-Whitney U test using scipy and interpret the results.

Focus on the function call and what the output numbers mean.